NEW Salford Predictive Modeler software suite. SPM Version 8.0 Just Released!
DOWNLOAD and try it for yourself today. Request an extended free 60-day trial. OR, See SPM 8
in action: SIGN UP FOR LIVE DEMO with Salford Systems’ CEO, Dr. Dan Steinberg.
SPM 8
- Brainpower:
- 70+ pre-packaged automation scenarios inspired by the way leading model analysts structure their work.
- Efficiencies:
- Tools to relieve gruntwork, allowing the analyst to focus on the creative aspects of model development.
- Enhanced Algorithms:
- Regression, Classification, and Logistic Regression enhanced to support massive datasets.
- Improvements:
- New features for our core tools, based on user feedback and advances in data science.
- Bridging-the-gap
- between the leading edge academic thinking of Jerome Friedman and Leo Breiman and real-world applications.
Because Accuracy Matters
The SPM Salford Predictive Modeler® software suite is a highly accurate and ultra-fast analytics and data mining platform for creating predictive, descriptive, and analytical models from databases of any size, complexity, or organization. This suite of data mining tools includes Salford Systems' flagship products of CART, MARS, TreeNet, and Random Forests. The SPM software suite's automation accelerates the process of model building by conducting substantial portions of the model exploration and refinement process for the analyst. While the analyst is always in full control, we optionally anticipate the analysts next best steps and package a complete set of results from alternative modeling strategies for easy review. Do in one day what normally requires a week or more using other systems!
[J#47:1604]
What's New
Salford Predictive Modeler® software suite: Faster. More Comprehensive Machine Learning. More Automation. Better results. Take a giant step forward in your data science productivity with SPM® 8.
- 70+ pre-packaged automation scenarios inspired by the way leading model analysts structure their work.
- Tools to relieve gruntwork, allowing the analyst to focus on the creative aspects of model development.
- Regression, Classification, and Logistic Regression enhanced to support massive datasets.
- New features for our core tools, based on user feedback and advances in data science.
- Bridging the gap between the leading edge academic thinking of Jerome Friedman and Leo Breiman and real-world applications.
- LATEST improvements: Our patented advances in decision tree models, our innovations in gradient boosting, and our extensive automation will all serve to make your analytical work day more productive and stress free. Take a giant step forward with SPM8
- Faster: SPM® 8 is more efficient in almost every area and leverages parallel processing on modern multiple core processors.
- More Data: SPM® 8 makes better use of RAM to run larger analytical problems.
- Easier: SPM® 8 builds in more automation driving quickly to better models.
- More exploratory tools: SPM® 8 includes more exploratory data analysis tools
- More machine learning: SPMv 8 includes a host of new loss functions for TreeNet Gradient Boosting supporting more accurate models.
- Uplift Model: SPM® 8 includes classical and new tools for differential lift modeling.
- More Controls: SPM® 8 has more options and fine tuning controls for the expert.
- Better Summaries: SPM® 8 has a new common performance summary for easy model comparison
- Better Interaction Discovery: SPM® 8 includes new GUI dialogs to guide use of the Interaction Control Language (ICL).
[J#49:1605]
Automation
New in SPM 8.0: 65 Pre-packaged scenarios, basically experiments, inspired by how leading model analysts structure their work. We call them "Automates." These "Automates" or experiments create multiple models automatically so that the analyst can easily see choices.
Example 1: Banking Applications
Automate Shaving
Automate Shaving helps to identify subsets of informative data within large datasets containing correlated variables within the account data. With automation, you may accomplish significant model reduction with minimal (if any) sacrifice to model accuracy. For example, start with a complete list of variables, and run automated shaving from the top to eliminate variables that look promising on the learn sample but fail to generalize. Later you can run shaving from the bottom to automatically eliminate a major bulk of redundant and unnecessary predictors. Then follow up with "shaving error" to quickly zero in on the most informative subset of features.
As opposed to typical data mining tools, Automate Shaving offers more than the typical variable importance list. Additionally, the analyst is provided with a full set of variable importance subsets/variations enabling the analyst to quickly optimize/select the final variable list and eliminating the burden of repetitive testing. Expert modelers typically devote a lot of time and effort to optimizing their variable importance list; Automate Shaving automates this process.
Example 2: Fraud Detection
Automate Priors
In typical fraud detection applications the analyst is concerned with identifying different sets of rules leading to a varying probability of fraud. Decision trees and TreeNet gradient boosting technology are typically used to build classification rules for detecting fraud. Any classification tree is constructed based on a specific user-supplied set of prior probabilities.
One set of priors will force trees to search for rules with high levels of fraud, while other sets of priors will produce trees with somewhat relaxed assumptions. To gain the most benefits of tree-based rule searching approaches, analysts will try a large number of different configurations of prior probabilities. This process is fully automated in Automate Priors. The result is a large collection of rules ranging from extremely high confidence fraud segments with low support to moderate indication of fraud segments with very wide support. For example, you can identify small segments with 100% fraud or you may find a large segment with a lesser probability of fraud, and everything in-between.
Example 3: Market Research - Surveys
Automate MVI (Missing Value Indicators)
In any survey, a large fraction of information may be missing. Often, the respondent will not answer questions either because they don't want to or are unable to do so. In addition to Salford Systems' expertise in handling missing values, a new automation feature allows the analyst to automatically generate multiple models including: 1) a model predicting response based solely on the pattern of missing values; 2) a model that automatically creates dummy missing value indicators in addition to the original set of predictors; and/or 3) a model that relies on engine-specific internal handling of missing values.
Example 4: Engineering Application
Automate Target
In a modern engineering application, as part of the experimental design, a large collection of sampled points may be gathered under different operating conditions. It can be challenging to identify mutual dependencies among the different parameters. For example, temperatures could be perfectly dependent on each other, or could be some unknown functions of other operating conditions like pressure and/or revolutions. Automate Target gives you powerful means to automatically explore and extract all mutual dependencies among predictors. By the word "dependencies," we mean a potentially nonlinear multivariate relationship that goes way beyond the simplicity of conventional correlations. Furthermore, as a powerful side effect, this Automate provides general means for missing value imputation, which is extremely useful to support those modeling engines that do not directly handle missing values.
Example 5: Web Advertising
Automate Sample
In an online ad placing application one has to balance the amount of data used vs. the time it takes to complete the model building. In web advertising there can be virtually an unlimited amount of data. So while ideally you would wish you use all available data, there is always a limit on how much can be used for real-time deployment. Automate Sample allows the analyst to automatically explore the impact of learn sample size on model accuracy. For example, you may discover that using 200,000,000 transactions provides no additional benefit in terms of model accuracy compared to 100,000,000 transactions.
Example 6: Microarray Application
Automate TARGETSHUFFLE
Microarray research datasets are characterized by an extremely large number of predictors (genes) and a very limited number of records (patients). This opens up a vast area of ambiguity resulting from the fact that even a random subset of predictors may produce a seemingly good looking model. Automate TARGETSHUFFLE allows you to determine whether the model performance is as accurate as it appears to be. Automate TARGETSHUFFLE automatically constructs a large number of auxiliary models based on randomly shuffled target variables. By comparing the actual model performance with the reference distribution (no dependency models), a final decision on model performance can be made. This technology could result in challenges to some of the currently produced papers in microarray research. If a dataset with deliberately destroyed target dependency can give you a model with good accuracy, then relying on the original model becomes rather dubious.
[J#50:1602]
User Guide
The Salford Predictive Modeler® Software Suite
Core components include CART®, MARS®, TreeNet®, Random Forests®, and Generalized PathSeeker
CART® Classification and Regression Trees
This guide describes the CART product and illustrates some practical examples of its basic usage and approach.
Welcome to CART, a robust decision-tree tool for data mining, predictive modeling, and data preprocessing. CART (Classification and Regresion Trees) automatically searches for important patterns and relationships, uncovering hidden structure even in highly complex data. CART trees can be used to generate accurate and reliable predictive models for a broad range of applications from bioinformatics to risk management and new applications are being reported daily.
Salford Systems' CART is the only decision-tree system based on the original CART code developed by world-renowned Stanford University and University of California at Berkeley statisticians Breiman, Friedman, Olshen and Stone.
[j#423:1602]
MARS® Multivariate Adaptive Regression Splines
This guide provides a brief introduction to MARS.
MARS, is considered the world’s first truly successful automated regression modeling tool. Multivariate Adaptive Regression Splines (MARS) has become widely known in the data mining and business intelligence worlds only recently through our seminars and the enthusiastic endorsement of leading data mining specialists. MARS is an innovative and flexible modeling tool that automates the building of accurate predictive models for continuous and binary dependent variables. It excels at finding optimal variable transformations and potential interaction within any regression-based modeling solution and easily handles the complex data structure that often hides in high-dimensional data. In doing so, this new approach to regression modeling effectively uncovers important data patterns and relationships that are difficult, if not impossible, for other methods to reveal.
[J#416:1602]
TreeNet® Stochastic Gradient Boosting
This guide describes the TreeNet product and illustrates some practical examples of its basic usage and approach.
TreeNet is a revolutionary advance in data mining technology developed by Jerome Friedman, one of the world's outstanding data mining researchers. TreeNet offers exceptional accuracy, blazing speed, and a high degree of fault tolerance for dirty and incomplete data. It can handle both classification and regression problems and has been proven to be remarkably effective in traditional numeric data mining and text mining.
[J#424:1602]
Random Forests®
This guide provides an introduction into RandomForests Modeling Basics.
This guide describes what’s under the hood, beginning with why RandomForests’ engine is both unique and innovative. Because RandomForests is such a new tool, we assume no prior knowledge of the adaptive modeling methodology underlying RandomForests. To put this methodology into context, the first section discusses the modeler’s challenge and addresses how RandomForests meets this challenge. The remaining sections provide detailed explanations of how the RandomForests model is generated, how RandomForests handles categorical variables and missing values, how the “optimal” model is selected and, finally, how testing regimens are used to protect against overfitting.
[J#426:1602]
GPS Generalized Path Seeker
This guide provides a brief introduction to GPS as well as a guide insight for model interpretation.
GPS or Generalized PathSeeker is a highly specialized and flexible regression (and logistic regression) procedure developed by Jerome Friedman (the co-creator of CART and the developer and inventor of MARS and TreeNet, among several other major contributions to data mining and machine learning). GPS is a "regularized regression" procedure meaning that it is designed to handle modeling challenges that are difficult or impossible for everyday regression.
[J#417:1602]
[J#61:1602]
Webinars
The Evolution of Regression Modeling
The Evolution of Regression Modeling: from Classical Linear Regression to Modern Ensembles
Webinar Title: The Evolution of Regression Modeling: from Classical Linear Regression to Modern Ensembles
Date/Time: Friday, March 1, 15, 29, and April 12 2013, 10am-11am, PST
Course Description: Regression is one of the most popular modeling methods, but the classical approach has significant problems. This webinar series address these problems. Are you are working with larger datasets? Is your data challenging? Does your data include missing values, nonlinear relationships, local patterns and interactions? This webinar series is for you! We will cover improvements to conventional and logistic regression, and will include a discussion of classical, regularized, and nonlinear regression, as well as modern ensemble and data mining approaches. This series will be of value to any classically trained statistician or modeler.
Part 1
Part 1: Regression methods discussed (download slides)
- Classical Regression
- Logistic Regression
- Regularized Regression: GPS Generalized Path Seeker
- Nonlinear Regression: MARS Regression Splines
The Evolution of Regression Modeling
Part 2
Part 1:Step-by-step demonstration
- Datasets and software available for download
- Instructions for reproducing demo at your leisure
- For the dedicated student: apply these methods to your own data (optional)
The Evolution of Regression Modeling
Part 3
Part 3: Regression methods discussed (download slides)
*Part 1 is a recommended pre-requisite
- Nonlinear Ensemble Approaches: TreeNet Gradient Boosting; Random Forests; Gradient Boosting incorporating RF
- Ensemble Post-Processing: ISLE; RuleLearner
The Evolution of Regression Modeling
Part 4
Part 4: Hands-on demonstration of concepts discussed in part 3 (download slides)
- Step-by-step demonstration
- Datasets and software available for download
- Instructions for reproducing demo at your leisure
- For the dedicated student: apply these methods to your own data (optional)
The Evolution of Regression Modeling
[J#58:1603]
Advances in TreeNet Gradient Boosting
Advances in Gradient Boosting: The Power of Post Processing
Advances in Gradient Boosting: the Power of Post-Processing
Learn how TreeNet stochastic gradient boosting can be improved by post processing techniques such as GPS Generalized Path Seeker, RuleLearner, and ISLE.Course Outline:
I. Gradient Boosting and Post-Processing:
- What is missing from Gradient Boosting?
- Why post-processing techniques are used?
II. Applications Benefiting from Post-Processing: Examples from a variety of industries.
- Financial Services
- Biomedical
- Environmental
- Manufacturing
- Adserving
III. Typical Post-Processing Steps
IV. Techniques
- Generalized Path Seeker (GPS): Modern high-speed LASSO-style regularized regression
- Importance Sampled Learning Ensembles (ISLE): identify and reweight the most influential trees
- RuleLearner: ISLE on “steroids.” Identify the most influential nodes and rules
V. Case Study Example
- Output/Results without Post-Processing
- Output/Results with Post-Processing
- Demo
Watch the Video
Advances in Gradient Boosting
[J#59:1603]
Combining CART and TreeNet
TreeNet Tree Ensembles and CART Decision Trees: A Winning Combination
TreeNet Tree Ensembles and CART Decision Trees: A Winning Combination
Combining CART decision trees with TreeNet stochastic gradient boosting: A winning combination.
Learn about how you can combine the best of both tools in this 1 hour webinar.
Course Outline
I. Classification and Regression Trees Pros/Cons
II. Stochastic Gradient Boosting: a promising way to overcome the shortcomings of a single tree
III. Introducing Stochastic Gradient Boosting, a powerful modern ensemble of boosted trees
- Methodology
- Reporting
- Interpretability
- Post-Processing
- Interaction Detection
IV. Advantages of using both Classification and Regression Trees and Tree Ensembles
Watch the Video
TreeNet Tree Ensembles and CART Decision Trees
[J#60:1603]
[J#62:1603]
University Program
Salford Systems' University Program provides SPM®, CART®, MARS®, TreeNet® , and RandomForests® at significantly-reduced licensing fees to the educational community. Eligible educational institutions are colleges, universities, community colleges, technical schools, and science centers. The University Program gives eligible educational institutions the right to distribute MARS and other Salford tools right-to-use licenses to all faculty, staff, and students for personal computers, and to install UNIX versions of these tools on University workstations and servers. For more information on this special program, please contact our sales department.
Salford Systems is committed to supporting education and research in universities world-wide and offers special packaging and pricing.
We also offer academics cost-free access to our tutorial materials for classroom use.
[J#65:1602]
Product Versions
SPM® 8 Product Versions
- Ultra
- The best of the best. For the modeler who must have access to leading edge technology available and fastest run times including major advances in ensemble modeling, interaction detection and automation. ULTRA also provides advance access to new features as they become available in frequent upgrades.
- ProEx
- For the modeler who needs cutting-edge data mining technology, including extensive automation of workflows typical for experienced data analysts and dozens of extensions to the Salford data mining engines.
- Pro
- A true predictive modeling workbench designed for the professional data miner. Variety of supporting conventional statistical modeling tools, programming language, reporting services, and a modest selection of workflow automation options.
- Basic
- Literally the basics. Salford Systems award winning data mining engines without extensions or automation or surrounding statistical services, programming language, and sophisticated reporting. Designed for small budgets while still delivering our world famous engines
[J#48:1603]
Requirements
-
We suggest the following minimum and recommended, system requirements:
- 80486 processor or higher.
- 512MB of random-access memory (RAM). This value depends on the "size" you have purchased (64MB, 128MB, 256MB, 512MB, 1GIG). While all versions may run with a minimum of 32MB of RAM, we CANNOT GUARANTEE they will. We highly recommend that you follow the recommended memory configuration that applies to the particular version you have purchased. Using less than the recommended memory configuration results in hard drive paging, reducing performance significantly, or application instability.
- Hard disk with 40 MB of free space for program files, data file access utility, and sample data files.
- Additional hard disk space for scratch files (with the required space contingent on the size of the input data set).
- CD-ROM or DVD drive.
Recommended System Requirements
Because Salford Tools are extremely CPU intensive, the faster your CPU, the faster they will run. For optimal performance, we strongly recommend they run on a machine with a system configuration equal to, or greater than, the following:
- Pentium 4 processor running 2.0+ GHz.
- 2 GIG of random-access memory (RAM). This value depends on the "size" you have purchased (64MB, 128MB, 256MB, 512MB, 1GIG). While all versions may run with a minimum of 32MB of RAM, we CANNOT GUARANTEE they will. We highly recommend that you follow the recommended memory configuration that applies to the particular version you have purchased. Using less than the recommended memory configuration results in hard drive paging, reducing performance significantly, or application instability.
- Hard disk with 40 MB of free space for program files, data file access utility, and sample data files.
- Additional hard disk space for scratch files (with the required space contingent on the size of the input data set).
- CD-ROM or DVD drive.
- 2 GIG of additional hard disk space available for virtual memory and temporary files.
Ensuring Proper Permissions
If you are installing on a machine that uses security permissions, please read the following note.
- You must belong to the Administrator group on Windows 2008, Windows 7 / 8 to be able to properly install and license. Once the application is installed and licensed, any member with read/write/modify permissions to the applications /bin and temp directories can execute and run the application.
-
Supported Architectures
- Alpha: DEC 3000 or AlphaServer running Tru64 UNIX 5.0 or higher
- Linux/i386: i586 or higher processor; Linux 2.4 or higher kernel; glibc 2.3 or higher
- Linux/AMD64: AMD64 or Intel EM64T processor; Linux 2.6 or higher kernel; glibc 2.3 or higher
- Sun: UltraSPARC processor; Solaris 2.6 or higher
- RS/6000: POWER or PowerPC processor; AIX 4.2 or higher
- HP 9000: PA/RISC 1.1 or higher processor; HP/UX 11.x
- SGI: MIPS 4 or higher processor; IRIX 6.5
Minimum System Requirements
- Minimum RAM requirement for all non-GUI app's is 32 MB of random-access memory (RAM). This value depends on the "size"
you have purchased (64MB, 128MB, 256MB, 512MB, 1GIG). - Hard disk with 40 MB of free space for program files, data file access utility, and sample data files.
- Additional hard disk space for scratch files (with the required space contingent on the size of the input data set).
Recommended System Requirements
- Recommended random-access memory (RAM) is 1.5 times the licensed data limit (32 MB, 64 MB, etc), up to the maximum permitted by the target architecture. On UNIX systems, it is generally recommended that there be at least twice as much swap space as there is RAM.
- Hard disk with 40 MB of free space for program files, data file access utility, and sample data files.
- Additional hard disk space for scratch files (with the required space contingent on the size of the input data set).
All Salford apps are very CPU intensive, so more memory and a faster CPU are always helpful.
Licensing Application
The Salford Predictive Modeler uses a system of application system ID and associated unlock key. When installation is complete, the user will need to email the application "system ID." This system ID is clearly displayed in the License Information displayed the first time the application is started. You can alternatively get to this window by selecting the Help->License menu option.
Method 1: Fixed License
With a fixed license, each machine must have its own copy of the licensed program installed. If your license terms permit more than one copy, then the license must be activated on each machine that will be used.
Method 2: Floating License
This method of licensing your program is used if you intend the program application to be used by more than one user concurrently over a network. A floating license tracks the number of copies "checked out." When that number exceeds your license terms, a message is provided informing the user "all copies are checked out." The licensed program may be installed on a machine that each client machine can access. Machines that are not connected to the network must be issued a fixed license (Method 1 above).
A floating license is particularly useful when the number of potential users exceeds the number of seats specified in your license terms.
[J#46:1609]
General Features
SPM® 8 General Features.
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engine: CART (Decision Trees) | o | o | o | o |
| Modeling Engine: MARS (Nonlinear Regression) | o | o | o | o |
| Modeling Engine: TreeNet (Stochastic Gradient Boosting) | o | o | o | o |
| Modeling Engine: RandomForests for Classification | o | o | o | o |
| Reporting ROC curves during model building and model scoring | o | o | o | o |
| Model performance stats based on Cross Validation | o | o | o | o |
| Model performance stats based on out of bag data during bootstrapping | o | o | o | o |
| Reporting performance summaries on learn and test data partitions | o | o | o | o |
| Reporting Gains and Lift Charts during model building and model scoring | o | o | o | o |
| Automatic creation of Command Logs | o | o | o | o |
| Built-in support to create, edit, and execute command files | o | o | o | o |
| Translating models into SAS ® -compatible language | o | o | o | o |
| Reading and writing datasets in all current database/statistical file formats | o | o | o | o |
| Option to save processed datasets into all current database/statistical file formats | o | o | o | o |
| Select Cases in Score Setup | o | o | o | o |
| TreeNet Scoring Offset in Score Setup | o | o | o | o |
| Setting of focus class supported for all categorical variables | o | o | o | o |
| Scalable limits on terminal nodes. This is a special mode that will ensure the ATOM and/or MINCHILD | o | o | o | o |
| Descriptive Statistics: Summary Stats, Stratified Stats, Charts and Histograms | o | o | o | |
| Activity Window: Brief data description, quick navigation to most common activities | o | o | o | |
| Additional Modeling Engines: Regularized Regression (LASSO/Ridge/LARS/Elastic Net/GPS) | o | o | o | |
| Data analysis Binning Engine | o | o | o | |
| Automatic creation of missing value indicators | o | o | o | |
| Option to treat missing value in a categorical predictor as a new level | o | o | o | |
| License to any level supported by RAM (currently 32MB to 1TB) | o | o | o | |
| License for multi-core capabilities | o | o | o | |
| Using built-in BASIC Programming Language during data preparation | o | o | o | |
| Automatic creation of lag variables based on user specifications during data preparation | o | o | o | |
| Automatic creation and reporting of key overall and stratified summary statistics for user supplied list of variables | o | o | o | |
| Display charts, histograms, and scatter plots for user selected variables | o | o | o | |
| Command Line GUI Assistant to simplify creating and editing command files | o | o | o | |
| Translating models into SAS/PMML/C/Java/Classic and ability to create classic and specialized reports for existing models | o | o | o | |
| Unsupervised Learning - Breiman's column scrambler | o | o | o | |
| Scoring any Automate (pre-packaged scenario of runs) as an ensemble model | o | o | o | |
| Summary statistics based on missing value imputation using scoring mechanism | o | o | o | |
| Impute options in Score Setup | o | o | o | |
| Quick Impute Analysis Engine: One-step statistical and model based imputation | o | o | o | |
| Advanced Imputation via Automate TARGET. Control over fill selection and new impute variable creation | o | o | o | |
| Correlation computation of over 10 different types of correlation | o | o | o | |
| Save OOB predictions from cross-validation models | o | o | o | |
| Custom selection of a new predictors list from an existing variable importance report | o | o | o | |
| User defined bins for Cross Validation | o | o | o | |
| Automation: Build two models reversing the roles of the learn and test samples (Automate FLIP) | o | o | o | |
| Automation: Explore model stability by repeated random drawing of the learn sample from the original dataset (Automate DRAW) | o | o | o | |
| Automation: For time series applications, build models based on sliding time window using a large array of user options (Automate DATASHIFT) | o | o | o | |
| Automation: Explore mutual multivariate dependencies among available predictors (Automate TARGET) | o | o | o | |
| Automation: Explore the effects of the learn sample size on the model performance (Automate LEARN CURVE) | o | o | o | |
| Automation: Build a series of models by varying the random number seed (Automate SEED) | o | o | o | |
| Automation: Explore the marginal contribution of each predictor to the existing model (Automate LOVO) | o | o | o | |
| Automation: Explore model stability by repeated repartitioning of the data into learn, test, and possibly hold-out samples (Automate PARTITION) | o | o | o | |
| Automation: Explore the nonlinear univariate relationships between the target and each available predictor (Automate ONEOFF) | o | o | o | |
| Automation: Bootstrapping process (sampling with replacement from the learn sample) with a large array of user options (Random Forests-style sampling of predictors, saving in-bag and out-of-bag scores, proximity matrix, and node dummies) (Automate BOOTSTRAP) *not available in RandomForests | o | o | o | |
| Automation: "Shift" the "crossover point" between learn and test samples with each cycle of the Automate (Automate LTCROSSOVER) | o | o | ||
| Automation: Build a series of models using different backward variable selection strategies (Automate SHAVING) | o | o | ||
| Automation: Build a series of models using the forward-stepwise variable selection strategy (Automate STEPWISE) | o | o | ||
| Automation: Explore nonlinear univariate relationships between each available predictor and the target (Automate XONY) | o | o | ||
| Automation: Build a series of models using randomly sampled predictors (Automate KEEP) | o | o | ||
| Automation: Explore the impact of a potential replacement of a given predictor by another one (Automate SWAP) | o | o | ||
| Automation: Parametric bootstrap process (Automate PBOOT) | o | o | ||
| Automation: Build a series of models for each strata defined in the dataset (Automate STRATA) | o | o | ||
| Automation: Build a series of models using every available data mining engine (Automate MODELS) | o | |||
| Automation: Run TreeNet for Predictor selection, Auto-bin predictors, then build a series of models using every available data mining engine (Automate GLM) | o | |||
| Modeling Pipelines: RuleLearner, ISLE | o | |||
| Build a CART tree utilizing the TreeNet engine to gain speed as well as alternative reporting | o | |||
| RandomForests inspired sampling of predictors at each node during model building | o | |||
| Build a RandomForests model utilizing the TreeNet engine to gain speed as well as alternative reporting | o | |||
| Build a Random Forests model utilizing the CART engine to gain alternative handling of missing values via surrogate splits (Battery BOOTSTRAP RSPLIT) | o |
[J#51:1602]
CART
Additional CART Features
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engine: CART (Decision Trees) | o | o | o | o |
| Linear Combination Splits | o | o | o | o |
| Optimal tree selection based on area under ROC curve | o | o | o | o |
| User defined splits for the root node and its children | o | o | o | |
| Translating models into Topology | o | o | o | |
| Manually edit and modify the CART trees via FORCE command structures | o | o | o | |
| Automation: Generate models with alternative handling of missing values (Automate MISSING_PENALTY) | o | o | o | |
| Automation: Build a series of models using all available splitting strategies (six for classification, two for regression) (Automate RULES) | o | o | o | |
| Automation: Build a series of models varying the depth of the tree (Automate DEPTH) | o | o | o | |
| Automation: Build a series of models changing the minimum required size on parent nodes (Automate ATOM) | o | o | o | |
| Automation: Build a series of models changing the minimum required size on child nodes (Automate MINCHILD) | o | o | o | |
| Automation: Explore accuracy versus speed trade-off due to potential sampling of records at each node in a tree (Automate SUBSAMPLE) | o | o | o | |
| Automation: Generates a series of N unsupervised-learning models (Automate UNSUPERVISED) | o | o | o | |
| Automation: Varies the RIN (Regression In the Node) parameter through the series of values (Automate RIN) | o | o | o | |
| Automation: Varying the number of "folds" used in cross-validation (Automate CVFOLDS) | o | o | o | |
| Automation: Repeat cross-validation process many times to explore the variance of estimates (Automate CVREPEATED) | o | o | o | |
| Automation: Build a series of models using a user-supplied list of binning variables for cross-validation (Automate CVBIN) | o | o | o | |
| Automation: Check the validity of model performance using Monte Carlo shuffling of the target (Automate TARGETSHUFFLE) | o | o | o | |
| Automation: Build two linked models, where the first one predicts the binary event while the second one predicts the amount (Automate RELATED). For example, predicting whether someone will buy and how much they will spend | o | o | o | |
| Automation: Indicates whether a variable importance matrix report should be produced when possible (Automate VARIMP) | o | o | o | |
| Automation: Saves the variable importance matrix to a comma-separated file (Automate VARIMPFILE) | o | o | o | |
| Hotspot detection for Automate UNSUPERVISED | o | o | ||
| Hotspot detection for Automate TARGET | o | o | ||
| Hotspot detection to identify the richest nodes across the multiple trees | o | o | ||
| Differential Lift Modeling (Netlift/Uplift) | o | o | ||
| Profile tab in CART Summary window | o | o | ||
| Multiple user defined lists for linear combinations | o | o | ||
| Constrained trees | o | o | ||
| Ability to create and save dummy variables for every node in the tree during scoring | o | o | ||
| Report basic stats on any variable of user choice at every node in the tree | o | o | ||
| Comparison of learn vs. test performance at every node of every tree in the sequence | o | o | ||
| Automation: Vary the priors for the specified class (Automate PRIORS) | o | o | ||
| Automation: Build a series of models by progressively removing misclassified records thus increasing the robustness of trees and posssibly reducing model complexity (Automate REFINE) | o | o | ||
| Automation: Bagging and ARCing using the legacy code (COMBINE) | o | o | ||
| Automation: Build a series of models limiting the number of nodes in a tree (Automate NODES) | o | o | ||
| Automation: Build a series of models trying each available predictor as the root node splitter (Automate ROOT) | o | o | ||
| Automation: Explore the impact of favoring equal sized child nodes by varying CART’s end cut parameter (Automate POWER) | o | o | ||
| Automation: Explore the impact of penalty on categorical predictors (Automate PENALTY=HLC) | o | o | ||
| Automation: Explore the impact of penalty on missing balues (Automate PENALTY=MISSING) | o | o | ||
| Build a Random Forests model utlizing the CART engine to gain alternative handling of missing values via surrogate splits (Automate BOOTSTRAP RSPLIT) | o |
[J#52:1603]
MARS
Additional MARS Features
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engine: MARS (Nonlinear Regression) | o | o | o | o |
| Save MARS basis functions in Score Setup | o | o | o | |
| Automation: Build a series of models varying the maximum number of basis functions (Automate BASIS) | o | o | o | |
| Automation: Varying the number of "folds" used in cross-validation (Automate CVFOLDS) | o | o | o | |
| Automation: Repeat cross-validation process many times to explore the variance of estimates (Automate CVREPEATED) | o | o | o | |
| Automation: Build a series of models using a user-supplied list of binning variables for cross-validation (Automate CVBIN) | o | o | o | |
| Automation: Build a series of models varying the smoothness parameter (Automate MINSPAN) | o | o | ||
| Automation: Build a series of models varying the order of interactions (Automate INTERACTIONS) | o | o | ||
| Automation:Build a series of models varying the modeling speed (Automate SPEED) | o | o | ||
| Automation: Explore the impact of penalty on categorical predictors (Automate PENALTY=HLC) | o | o | ||
| Automation: Explore the impact of penalty on missing balues (Automate PENALTY=MISSING) | o | o | ||
| Automation: Build a series of models using varying degree of penalty on added variables (Automate PENALTY MARS) | o |
[J#53:1603]
TreeNet
Additional TreeNet Features
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engine: TreeNet (Stochastic Gradient Boosting) | o | o | o | o |
| Spline-based approximations to the TreeNet dependency plots | o | o | o | |
| Exporting TreeNet dependency plots into XML file | o | o | o | |
| Interactions: allow interactions penalty which inhibits TreeNet from introducing new variables (and thus interactions) within a branch of a tree | o | o | o | |
| Automation: Build a series of models changing the minimum required size on child nodes (Automate MINCHILD) | o | o | o | |
| Automation: Varying the number of "folds" used in cross-validation (Automate CVFOLDS) | o | o | o | |
| Automation: Repeat cross-validation process many times to explore the variance of estimates (Automate CVREPEATED) | o | o | o | |
| Automation: Build a series of models using a user-supplied list of binning variables for cross-validation (Automate CVBIN) | o | o | o | |
| Automation: Check the validity of model performance using Monte Carlo shuffling of the target (Automate TARGETSHUFFLE) | o | o | o | |
| Automation: Indicates whether a variable importance matrix report should be produced when possible (Automate VARIMP) | o | o | o | |
| Automation: Saves the variable importance matrix to a comma-separated file (Automate VARIMPFILE) | o | o | o | |
| Auto creation of new spline-based approximation variables. One step creation and savings of transformed variable to new dataset | o | o | ||
| Automation: Build two linked models, where the first one predicts the binary event while the second one predicts the amount (Automate RELATED). For example, predicting whether someone will buy and how much they will spend | o | o | ||
| Flexible control over interactions in a TreeNet model(ICL) | o | o | ||
| Interaction strength reporting | o | o | ||
| Interactions: Generate reports describing pairwise interactons of predictors | o | o | ||
| Subsample separately by target class. Specify separate sampling rates for the target classes in binary logistic models | o | o | ||
| Control number of top ranked models for which performance measures will be computed and saved | o | o | ||
| Advanced controls to reduce required memory (RAM) | o | o | ||
| Extended Influence Trimming Controls: ability to limit influence trimming to focus class and/or correctly classified | o | o | ||
| Differential Lift Modeling (Netlift/Uplift) | o | o | ||
| QUANTILE specifies which quantile will be used during LOSS=LAD | o | o | ||
| POISSON: Designed for the regression modeling of integer COUNT data | o | o | ||
| GAMMA distribution loss, used strictly for positive targets | o | o | ||
| NEGBIN: Negative Binomial distribution loss, used for counted targets (0,1,2,3,…) | o | o | ||
| COX where the target (MODEL) variable is the non-negative survival time while the CENSOR variable indicates | o | o | ||
| Tweedie loss function | o | o | ||
| Automation: Build a series of models limiting the number of nodes in a tree (Automate NODES) | o | o | ||
| Automation: Convert (bin) all continuous variables into categorical (discrete) versions using a large array of user options (equal width, weights of evidence, Naïve Bayes, supervised) (Automate BIN) | o | o | ||
| Automation: Produces a series of three TreeNet models, making use of the TREATMENT variable specified on the TreeNet command (Automate DIFFLIFT) | o | o | ||
| Automation: Build a series of mdoels varying the speed of learning (Automate LEARNRATE) | o | o | ||
| Automation: Build a series of models by progressively imposing additivity on individual predictors (Automate ADDITIVE) | o | o | ||
| Automation: Build a series of models utilizing different regression loss functions (Automate TNREG) | o | o | ||
| Automation: Build a series of models by varying subsampling fraction (Automate TNSUBSAMPLE) | o | o | ||
| Automation: Build a series of models using varying degree of penalty on added variables (Automate ADDEDVAR) | o | o | ||
| Modeling Pipelines: RuleLearner, ISLE | o | |||
| Build a CART tree utilizing the TreeNet engine to gain speed as well as alternative reporting | o | |||
| Build a RandomForests model utilizing the TreeNet engine to gain speed as well as alternative reporting | o | |||
| RandomForests inspired sampling of predictors at each node during model building | o | |||
| Automation: Explore the impact of influence trimming (outlier removal) for logistic and classification models (Automate INFLUENCE) | o | |||
| Automation: Exhaustive search and ranking for all interactions of the specified order (Automate ICL) | o | |||
| Automation: Varies the number of predictors that can participate in a TreeNet branch, using interaction controls to constrain interactions (Automate ICL NWAY) | o |
[J#54:1603]
Random Forest
Additional Random Forests Features are available in Pro, ProEx, and Ultra.
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engine: RandomForests for Classification | o | o | o | o |
| Additional Modeling Engine:RandomForests for Regession | o | o | o | |
| Automation: Varies the bootstrap sample size (Automate RFBOOTSTRAP) | o | o | o | |
| Automation: Vary the number of randomly selected predictors at the node-level (Automate RFNPREDS) | o | o | o | |
| Flexible controls over interactions in a Random Forests for Regression model (requires TreeNet license) | o | |||
| Interaction strength reporting (requires TreeNet license) | o | |||
| Spline-based approximations to the Random Forests for Regression dependency plots (requires TreeNet license) | o | |||
| Exporting Random Forests for Regression dependency plots into XML files (requires TreeNet license) | o | |||
| Build a CART tree utilizing the Random Forests for Regression engine to gain speed as well as alternative reporting | o | |||
| Automation: Explore the impact of influence trimming (outlier removal) for logistic and classification models (Automate INFLUENCE) | o | |||
| Automation:Exhaustive search and ranking for all interactions of the specified order (Automate ICL) | o |
[J#55:1609]
GPS
Additional GPS Generalized Path Seeker Features
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Modeling Engines:Regularized Regression (LASSO/Ridge/LARS/Elastic Net/GPS) |
o | o | ||
| Automation: Build a series of models by forcing different limit on the maximum correlation among predictors (Automate MAXCORR) | o | o |
[J#56:1603]
OLS
Additional OLS Regression Features
| Components | Basic | Pro | ProEx | Ultra |
|---|---|---|---|---|
| Components | Basic | Pro | ProEx | Ultra |
| Automation: Generate detailed univariate distributional reports for every continuous variable on the KEEP list (Automate OUTLIERS) | o | o |
[J#441:1603]
Testimonials
Rawa Shamroukh, Union Bank, Vice President / Senior Strategic Modeling Manager, Predictive Modeling Department
Using Salfords’ data mining Software TreeNet and CART for the last 8 years, Union Bank has developed multiple in-house statistical models for the various business units within Retail Banking. These tools have greatly expanded our ability to synthesize massive amounts of data quickly, reduce our modeling turn around-times, and mainly produce the most robust predictive models in terms of accuracy and performance. The main benefits from these tools from the bank’s perspective are time savings, Productivity increase, superior analytics, and affordable tools. Treenet and CART provided significant advantages and established a new paradigm for certain modeling challenges within our department. Benefits were obtained along each step of the overall data mining process from data processing to model development and implementation. It demonstrates remarkable performance for both regression and classification models. When I first started using Treenet for logistic Regression Modeling, I always used to develop a parallel model using basic SAS. Treenet kept outperforming SAS logistic regression models over and over. In my opinion, the most amazing features in these tools are their automatic handling of variables selection, collinearity, data transformation, outliers, and many more. In addition, you can have on-the-spot model assessment by generating immediate Gain / Lift charts, ROC measures, Train/ test comparison, Misclassification / prediction success, etc. Using these tools, you will have the options to deploy your final model in a SAS environment or a SQL environment since they automatically translates your model into SAS codes, C codes, or PMML codes. I have used Treenet in various applications. To name few: Attrition models, Behavior scoring models, Operation losses models, Overdraft models, Uncollected funds models, Fraud models, etc.
Rawa Shamroukh
Union Bank
Vice President / Senior Strategic Modeling Manager
Predictive Modeling Department
Sassoon Kosian, Sr. Assistant Vice President and Head of Methodology at EXL Service
In the Decision Analytics practice of EXL Service we build many predictive models for our clients representing a wide range of industries, levels of complexity and application environments. CART and MARS have been standard tools that our resources are trained on and apply in model development. I personally have been using Salford Systems products for nearly 8 years and I believe will continue using them for the foreseeable future. I have mostly used CART and sometimes MARS, and in recent years also tried Random Forests and TreeNet. All of the products offer an intuitive GUI interface and versatility but for me personally CART would be the winner.
When it comes to decision trees there are other options in the market but none has come close to CART in terms of rich functionality, intuitive ease of use and affordability. These are reasons why I continue recommending it to our modeling resources. There several ways we take advantage of CART features. First of all, it is quite easy and quick to build a CART tree with decent predictive power and which you can also explain to business users - something that's very important to our clients. Besides building tree models we often use CART to quickly derive insights about the data by building a preliminary tree and exploring the variable importance list, important nodes and making sense of individual variables. I find the data exploration functionality incredibly valuable especially when you have hundreds or thousands of variables. CART and MARS have also helped us to create composite variables that we have used in regression models - another very useful feature we frequently use. CART also comes in handy to quickly identify segmentation strategies in complex scenarios. All of these features make CART a very important tool in our model development toolkit and help us bring value to our clients.
Sassoon Kosian, Sr. Assistant Vice President and Head of Methodology at EXL Service
Xu Jie, Nanjing University of Information Science & Technology
I am conducting a project about GIS, in which many data analysis are needed. Lacking useful tools, our project made slow progress. In an accidental chance I got a TreeNet trial version and it shocked me with its powerful capabilities of data analyzing, friendly user interface and most important of all, accuracy. After using it we got many benefits from it during our research and our project had gone much faster.
In many features of TreeNet, we like most is plots which offers graphs displaying after building model. This feature is especially useful to us which provides the most visual and easy way to find shortcomings and make improvement of the model. We like the multiple model setting up ways as well, it’s flexible and covers most aspects of our research.
What attracts me most is the amazing speed of TreeNet. We have used some other software before using TreeNet. None of them could build a model in such a short time. What’s more, using TreeNet, the painstaking procedures of data preprocessing are saved, it greatly accelerated our research. Since our data contains over 100 million of variables, using common software, it takes weeks to get a result of analyze. However, by using TreeNet, it takes just a couple of days.
In addition, the most important is the accuracy. Due to the defects of sampling stage, there are some noisy variables in our data, which brings instability to our model. By using TreeNet, we got more stable model of our research than by other tools. What’s more, the model we built by TreeNet could be repeated and verified.
As to ROI, I cannot say how much money we have saved by using this tool, but we did consider to buy a high performance computer(about 5000 US dollars)to assist our research. After using the software, we decided to postpone that purchasing.
We are getting to use TreeNet just a few months , but we really impressed by its powerfulness. We know we are using just a few common features, a lot of powerful features are still waiting for us to learn.
Xu Jie, Nanjing University of Information Science & Technology
Megan Sun, Data Mining Analyst, Marketing Department at Genworth Financial
I have 6 years using SAS and other statistical software to conduct academic and business projects. I started using SPM to build predictive models in May 2014. Our team mainly uses SPM TreeNet to build models for direct mail campaigns. I think the SPM software (Salford Predictive Modeler) is S.P.M. - SMART, PRODUCTIVE and MANAGEABLE.
Megan Sun, Data Mining Analyst,
Marketing Department at Genworth Financial
Brian Griner, Chief Methodologist at Quintiles
The Salford Predictive Modeler Software Suite
Great product! Very easy to test different models, compare results and export code to score a database.
Brian Griner, Chief Methodologist at Quintiles
New York, USA
Jim Kenyon, Director of Operations for Optimization Group.
We use SPM because it lets us quickly and easily build predictive models that produce useful and usable results for our clients.
Jim Kenyon, Director of Operations at Optimization Group
Ann Arbor, MI, USA
[J#64:1602]
[j#38:1603]